0xSoul 发表于 2023-6-7 23:06:42

[SD 1.5][TextualInversion]hitokomoru-style-nao learned embeds

<p>最初发布于<a href="https://huggingface.co/sd-concepts-library/hitokomoru-style-nao" rel="ugc" target="_blank">HuggingFace</a>,作者为sd-concepts-library。</p>注意:使用了WAIFU DIFFUSION。<p><a href="https://huggingface.co/hakurei/waifu-diffusion" rel="ugc" target="_blank">https://huggingface.co/hakurei/waifu-diffusion</a></p>hitokomoru-style<p>艺术家:<a href="https://www.pixiv.net/en/users/30837811" rel="ugc" target="_blank">https://www.pixiv.net/en/users/30837811</a></p><p>这是通过文本反转向Stable Diffusion教授的&lt;hitokomoru-style&gt;概念。您可以将此概念加载到<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb" rel="ugc" target="_blank">稳定概念化器</a>笔记本中。您还可以训练自己的概念并将它们加载到概念库中,使用<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb" rel="ugc" target="_blank">此笔记本</a>。</p><p><br /></p>

Vigil49 发表于 2024-4-4 17:51:02

感谢分享
页: [1]
查看完整版本: [SD 1.5][TextualInversion]hitokomoru-style-nao learned embeds